How should Paper Polisher Pro — AI Detector & Academic Polishing be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Paper Polisher Pro — AI Detector & Academic Polishing

AI-rate self-check for academic writing, polish guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label check (China 2025-09 labeling rules), paragraph-level attribution, journal precheck, sentence-level rewrite suggestions (locates and advises, never auto-rewrites), plus `--batch DIR` for thesis-scale batch rewriting (per-file AI-rate scores directory-wide). Bilingual CN/EN, 100% local, zero upload, zero credentials; bundled unit-test suite + AST-based zero-network self-verification. v3 delivers a recalibrated multi-layer rule engine (11 core layers + discourse/smoothness heuristics) + token-spectrum layer + length-routed fusion + optional supervised Qwen3-0.6B ONNX layer (AUROC 1.0 on held-out test) + LLM fingerprint attribution (GLM/DeepSeek/Qwen/Kimi/MiniMax/GPT/Claude/Gemini) + freshness pipeline. Base-engine numbers reproduce from the bundled held-out evaluation; supervised columns are author-side measurements (model not bundled). Skill: Paper Polisher Pro — AI Detector & Academic Polishing Owner: docsor1212 Summary: AI-rate self-check for academic writing, polish guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label check (China 2025-09 labeling rules), paragraph-level attribution, journal precheck, sentence-level rewrite suggestions (locates and advises, never auto-rewrites), plus --batch DIR

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.8k

Updated

Oct 10, 2026

Version

5.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.8K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.8K downloadsadoption · observed Oct 10, 2026
Latest release: 5.1.0release · observed Oct 9, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17dagtwyk21qs6vpz98bzcrh1853t29:paper-polisher-pro

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-docsor1212-paper-polisher-pro/snapshot"

Documentation

CLAWHUB

160,000 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: paper-polisher
version: 5.1.0
author: DoctorQ Lab
description: >-
  AI-rate self-check for academic writing, polish guidance (style, terminology, translation-smell),
  metaphor audit, quality report, AIGC compliance label check (China 2025-09
  labeling rules), paragraph-level attribution, journal precheck, sentence-level
  rewrite suggestions (locates and advises, never auto-rewrites), plus `--batch DIR`
  for thesis-scale batch rewriting (per-file AI-rate scores directory-wide).
  Bilingual CN/EN, 100% local, zero upload, zero credentials; bundled unit-test suite
  + AST-based zero-network self-verification.
  v3 delivers a recalibrated multi-layer
  rule engine (11 core layers + discourse/smoothness heuristics) + token-spectrum layer + length-routed fusion + optional
  supervised Qwen3-0.6B ONNX layer (AUROC 1.0 on held-out test) + LLM
  fingerprint attribution (GLM/DeepSeek/Qwen/Kimi/MiniMax/GPT/Claude/Gemini) +
  freshness pipeline. Base-engine numbers reproduce from the bundled held-out
  evaluation; supervised columns are author-side measurements (model not bundled).
tags: [ai-detection, deai, academic-writing, paraphrase, paper-polish]
---

# Paper Polisher Pro v3

AI writing detection (AI-rate self-check for authors) · academic polishing guidance · terminology standardization · translation-smell check · quality report · AIGC compliance label check · paragraph-level attribution · journal precheck.
100% local, zero upload, zero credentials, pure standard library (optional onnxruntime enhancement layer).

> ## ⛔ Iron laws
> 1. **Only reproducible numbers.** Every metric comes from the held-out (test split) evaluation in `eval/run_eval.py`; unsupported claims like "100% detection rate / F1 98.3%" from older docs have been removed.
> 2. **No verdict on short text.** Texts under 100 characters get `risk=unknown` (community lesson: short-text false positives are uncontrollable).
> 3. **Fingerprints attribute, never score.** (Measured 2026-08-15: injecting fingerprints into the detector doubled human false positives.)
> 4. **Calibration/evaluation separation.** Spectrum, weights and thresholds are built on the calib half only; the test half is reserved for final evaluation (an in-sample AUROC of 0.9972 collapsed to a real 0.9187 once split).

## TL;DR

- **What**: 100% local AI-rate self-check + academic polishing toolkit for Chinese academic text (optional supervised model for best accuracy; English gets advisory rules-only scores).
- **30-second start**: `python3 scripts/pp.py quickstart` (zero-model, zero-file demo) · `python3 scripts/pp.py detect draft.txt --format json` · sentence-level rewrite suggestions: `python3 scripts/pp.py fix draft.txt` · full self-check report: `python3 scripts/pp.py workflow draft.txt` · environment: `python3 scripts/pp.py doctor` (one entry routes all subcommands)
- **Measured** (held-out, fingerprint-bound md5 2631df3d388b): AUROC 0.9998 pre-2026 / 0.9400 current-generation; human FPR@medium 2.3%.
- **

README.md

# Paper Polisher Pro — 论文降AI润色工具 · AI率检测

[![GitHub Stars](https://img.shields.io/github/stars/docsor1212/paper-polisher-pro?style=social&label=Star)](https://github.com/docsor1212/paper-polisher-pro)

AI 痕迹检测（AI率）· 去AI化改写建议 · 句子级改写建议（哪几句像AI、怎么改）· 术语标准化 · 翻译腔检查 · 质量报告 · AIGC 合规标识检查 · 段落级归因 · 期刊口径预检。

**100% 本地运行，零上传，零凭证**——论文数据不出本机。零网络承诺可用包内 `pp_verify.py`（AST 结构化扫描）自行验证，行为契约可用随包 `tests/` 单元测试套件（44 用例）在自己机器上复跑。

## 这是什么

面向学术写作者的 AI 痕迹自查工具：概率化输出（非二元判定）、分层证据、指纹归因（GLM / DeepSeek / Qwen / Kimi / MiniMax / GPT / Claude / Gemini），全部指标可由随包留出集评测复现。

- 基础引擎（纯规则+词频谱）：留出集 AUROC 0.9187
- 可选监督层（本地 Qwen3-0.6B ONNX）：AUROC 1.0（作者侧实测）
- 短文本不出判定（<100 字，误报铁律）

## 快速开始

```bash
# 零模型零文件一键体验
python scripts/pp.py quickstart

# AI 痕迹检测（AI率）
python scripts/ai_detector.py draft.txt --format json

# 句子级改写建议（定位+策略，不代改）
python scripts/pp_fix_suggest.py draft.txt --top 10

# 四层融合门禁
python scripts/deai_gate.py draft.txt

# 批量检测一个目录
python scripts/ai_detector.py --batch ./drafts --csv scores.csv

# 环境自检
python scripts/pp_doctor.py

# Python 编程接口（零网络，import 即用）
python -c "import sys; sys.path.insert(0,'scripts'); from pp_api import detect_text; \
print(detect_text(open('draft.txt').read())['overall_ai_score'])"

# 监督层一键装模（作者签发模型文件，指纹校验+推理自检）
python scripts/pp_setup.py --model <作者签发模型.onnx>
```

## 安装

克隆本仓库后直接使用，纯 Python 标准库即可运行（可选 onnxruntime 增强监督层，依赖声明见 `requirements.txt`）。

```bash
git clone https://github.com/docsor1212/paper-polisher-pro
cd paper-polisher-pro
python scripts/ai_detector.py your_draft.txt --format summary
```

**China mirror (ModelScope 魔搭)**: <https://modelscope.cn/skills/Docsor/paper-polisher-pro> — if you find this skill useful, a like there helps others find it.

## 论文工作流家族

写作是一条链，每环有专用工具（均在本账号下）：

| 工具 | 用途 |
|---|---|
| **paper-polisher-pro**（本仓库） | AI率检测·润色·降重·质量报告 |
| **paper-rewriter** | 论文降AI改写执行 |
| **pubmed-verifier** | PMID/DOI 引用核验 |
| **cite-holmes** | 深度调研 × 引用自证 |
| **cn-med-oa** | 中文医学文献 OA 下载 |
| **academic-figures** | 出版级科研图表 |
| **doc-holmes** | PDF 精准翻译 |

文档站：[docsor.cn](https://docsor.cn)

## 合规声明

本工具供作者自查与写作质量改进，**不用于规避机构的 AIGC 检测**；请遵循所在机构的 AI 使用与披露政策（标识合规可用包内 aigc_label_check 自查）。许可：MIT-0。

_meta.json

{
  "ownerId": "kn7b6sjwend7cwwmhf7mdg1wzx82dfbf",
  "slug": "paper-polisher-pro",
  "version": "5.1.0",
  "publishedAt": 1791565192833
}

references/ai_patterns_en.json

{
  "version": "3.1.0",
  "description": "English AI writing pattern library",
  "categories": {
    "filler_phrases": {
      "weight": 3,
      "description": "High-frequency AI filler phrases (strong signal)",
      "patterns": [
        "it is worth noting that",
        "it is important to note that",
        "it should be noted that",
        "it is worth mentioning that",
        "it is crucial to understand",
        "it is essential to recognize",
        "it is imperative to",
        "it is paramount to",
        "in conclusion",
        "to summarize",
        "in summary",
        "to sum up",
        "all in all",
        "at the end of the day",
        "when all is said and done",
        "needless to say",
        "it goes without saying",
        "as a matter of fact",
        "in today's world",
        "in this day and age",
        "in the modern world",
        "in recent years",
        "with the development of",
        "with the advancement of",
        "in the era of",
        "in the age of",
        "plays a crucial role",
        "plays a vital role",
        "plays an important role",
        "plays a significant role",
        "is of paramount importance",
        "is of great significance",
        "has gained significant attention",
        "has attracted considerable attention",
        "has been widely studied",
        "has been extensively investigated",
        "a growing body of evidence",
        "an increasing number of",
        "a wide range of",
        "a variety of",
        "a plethora of",
        "a myriad of",
        "delve into",
        "shed light on",
        "pave the way for",
        "open new avenues",
        "bridge the gap",
        "furthermore",
        "moreover",
        "additionally",
        "consequently",
        "nevertheless",
        "nonetheless",
        "subsequently",
        "notably",
        "specifically",
        "fundamentally",
        "intriguingly",
        "notably",
        "remarkably",
        "underscores the importance",
        "highlights the significance",
        "serves as a testament",
        "poised to",
        "tailored to",
        "groundbreaking",
        "pivotal",
        "indispensable",
        "multifaceted",
        "nuanced",
        "comprehensive",
        "robust",
        "state-of-the-art",
        "cutting-edge"
      ]
    },
    "conclusion_patterns": {
      "weight": 4,
      "description": "AI-typical conclusion patterns",
      "patterns": [
        "in conclusion,?.{0,30}(important|significant|crucial)",
        "this study (demonstrates|shows|reveals|suggests) that",
        "these findings (suggest|indicate|demonstrate|highlight)",
        "future research (should|could|may|might) (focus|explore|investigate|examine)",
        "the results of this study (provide|offer|contribute)",
        "this research (contributes|adds|provides) (to|a|new)",
        "taken together,?.{0,20}(suggest|indicate|demonstrate)",
        "over

references/ai_patterns_zh.json

{
  "version": "4.0.0",
  "description": "v3数据驱动重校准版 (基线语料实测FPR过滤)",
  "recalibration": {
    "date": "2026-08-15",
    "corpus": "eval/corpora_small/eval_zh.jsonl",
    "humans": 245,
    "ais": 1645,
    "dropped": 568,
    "demoted": 5
  },
  "categories": {
    "weak_signals": {
      "weight": 1,
      "description": "v3重校准: 人类语料命中3%+且lift<2的弱信号, 仅组合计分(单独命中不足以判AI)",
      "patterns": [
        "然后",
        "因此",
        "再次",
        "似乎",
        "先.*再.*"
      ]
    },
    "filler_phrases": {
      "weight": 3,
      "description": "各模型通用AI高频填充短语",
      "patterns": [
        "值得注意的是",
        "综上所述",
        "总而言之",
        "具体而言",
        "深入探讨",
        "深入理解",
        "系统梳理",
        "深入分析",
        "旨在探讨",
        "具有重要意义",
        "提供了新的视角",
        "奠定了基础",
        "本文旨在",
        "本研究旨在",
        "本研究通过",
        "本研究为",
        "与此同时",
        "在此基础上",
        "尤其是",
        "特别是",
        "不容忽视",
        "至关重要",
        "关键作用",
        "重要意义",
        "不可忽视"
      ]
    },
    "ai_cliches": {
      "weight": 4,
      "description": "AI标志性套话和陈词滥调（最强信号）",
      "patterns": [
        "令人印象深刻",
        "令人满意",
        "新思路",
        "日益受到",
        "不断完善",
        "展现出.*潜力",
        "展现出.*价值",
        "为.*提供了新",
        "值得关注",
        "引起了广泛关注",
        "为.{2,15}(铺平|奠定|打开)了.{2,10}(道路|基础|大门|新方向)"
      ]
    },
    "conclusion_patterns": {
      "weight": 4,
      "description": "AI标志性结尾模式",
      "patterns": [
        "本研究(为|对).{0,30}(提供了|具有一定的)",
        "研究结果.{0,20}(表明|显示|证实)"
      ]
    },
    "transition_words": {
      "weight": 2,
      "description": "AI过度使用的过渡词",
      "patterns": [
        "此外",
        "同时",
        "然而",
        "与此同时",
        "另一方面",
        "进一步地",
        "总的来说",
        "首先",
        "其次"
      ]
    },
    "sentence_structure": {
      "weight": 2,
      "description": "AI典型句式特征",
      "patterns": [
        "不仅.{2,20}而且.{2,30}",
        "不仅.{2,20}还.{2,30}",
        "既.{2,15}又.{2,15}",
        "一方面.{5,40}另一方面.{5,40}",
        "通过.{2,30}实现了.{2,30}",
        "通过.{2,30}为.{2,30}(提供了|奠定了)",
        "随着.{2,20}的(发展|深入|推进|不断|广泛)",
        "对于.*来说",
        "对.*而言",
        "作为.*的.*之一",
        "在.*中(扮演|发挥|起到)"
      ]
    },
    "vague_expressions": {
      "weight": 2,
      "description": "AI倾向使用的模糊表达",
      "patterns": [
        "在一定程度上",
        "整体而言",
        "可以说",
        "总体而言",
        "总体来说"
      ]
    },
    "redundant_expressions": {
      "weight": 1,
      "description": "AI冗余表达",
      "patterns": [
        "进行(了)?(深入|详细|全面|系统)的?(分析|研究|探讨|阐述)",
        "对.{2,15}进行了.{2,15}(分析|研究|探讨)",
        "进行了.*分析",
        "进行了.*研究",
        "进行了.*探讨"
      ]
    },
    "deepseek_fingerprint": {
      "weight": 4,
      "description": "DeepSeek模型指纹：教科书体+数据驱动+编号结构（最强信号）",
      "patterns": [
        "大规模.*研究"
      ]
    },
    "glm_fingerprint": {
      "weight": 3,
      "description": "GLM/智谱模型指纹：四平八稳综述体",
      "patterns": [
        "关注的焦点",
        "确保.*安全",
        "以确保.*安全"
      ]
    },
    "

Github ReposUpdated 10h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.